feat(rag): embedding model support & rag improvements #192
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,10 +1,11 @@ | ||
| from dataclasses import dataclass | ||
| from typing import Union | ||
| from rag_ingestion.processors.file_processor import DocumentType | ||
|
|
||
|
|
||
| @dataclass | ||
| class DocContent: | ||
| """Model representing the extracted content from a document file""" | ||
|
|
||
| content: Union[str, bytes] | ||
| document_type: DocumentType |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,48 +1,59 @@ | ||
| import os | ||
| import tempfile | ||
| import textract | ||
| from typing import Tuple | ||
| from enum import Enum | ||
| from common_module.log.logger import logger | ||
|
|
||
|
|
||
| class DocumentType(Enum): | ||
| PDF = 'pdf' | ||
| IMAGE = 'image' | ||
| TEXT = 'text' | ||
|
|
||
|
|
||
| class FileProcessor: | ||
| def process_file( | ||
| self, file_content: bytes, file_type: str | ||
| ) -> Tuple[str | bytes, DocumentType]: | ||
| mime_type = file_type | ||
| document_type = self.extract_document_type(mime_type) | ||
| if document_type == DocumentType.TEXT: | ||
| return file_content.decode('utf-8'), DocumentType.TEXT | ||
|
|
||
| if document_type == DocumentType.IMAGE: | ||
| return file_content, DocumentType.IMAGE | ||
|
|
||
| if document_type == DocumentType.PDF: | ||
| with tempfile.NamedTemporaryFile( | ||
| mode='w+b', delete=False, suffix='.pdf' | ||
| ) as temp_file: | ||
| temp_file.write(file_content) | ||
| temp_file.flush() | ||
| temp_file_path = temp_file.name | ||
|
|
||
| try: | ||
| text_content = textract.process( | ||
| temp_file_path, method='pdfminer' | ||
| ).decode('utf-8') | ||
| return text_content, DocumentType.PDF | ||
|
|
||
| except Exception as e: | ||
| logger.error(f'Text extraction failed for {mime_type}: {e}') | ||
| raise RuntimeError(f'Text extraction failed for {mime_type}: {e}') | ||
|
Comment on lines
41
to
43
There was a problem hiding this comment. Improve exception handling with chaining and specific types. The exception handling has two issues:
Apply this diff: - except Exception as e:
+ except (textract.exceptions.ShellError, UnicodeDecodeError, OSError) as e:
logger.error(f'Text extraction failed for {mime_type}: {e}')
- raise RuntimeError(f'Text extraction failed for {mime_type}: {e}')
+ raise RuntimeError(f'Text extraction failed for {mime_type}: {e}') from eNote: Verify the specific exception types raised by textract if
🧰 Tools🪛 Ruff (0.14.8)41-41: Do not catch blind exception: (BLE001) 43-43: Within an (B904) 43-43: Avoid specifying long messages outside the exception class (TRY003) |
||
|
|
||
| finally: | ||
| os.unlink(temp_file_path) | ||
|
|
||
| # Explicit raise to prevent implicit None return. | ||
| raise RuntimeError(f'Unsupported or unknown document type: {document_type}') | ||
|
|
||
| def extract_document_type(self, file_type: str) -> DocumentType: | ||
| if file_type.startswith('text/plain'): | ||
| return DocumentType.TEXT | ||
| if file_type.startswith('image/'): | ||
| return DocumentType.IMAGE | ||
| if file_type in ('application/pdf', 'application/x-pdf'): | ||
| return DocumentType.PDF | ||
| else: | ||
| raise ValueError(f'Unsupported file type: {file_type}') | ||
|
Comment on lines
+51
to
+59
There was a problem hiding this comment. Implement case-insensitive MIME type matching. MIME types are case-insensitive per RFC 2045, but the current implementation uses case-sensitive Apply this diff: def extract_document_type(self, file_type: str) -> DocumentType:
- if file_type.startswith('text/plain'):
+ file_type_lower = file_type.lower()
+ if file_type_lower.startswith('text/plain'):
return DocumentType.TEXT
- if file_type.startswith('image/'):
+ if file_type_lower.startswith('image/'):
return DocumentType.IMAGE
- if file_type in ('application/pdf', 'application/x-pdf'):
+ if file_type_lower in ('application/pdf', 'application/x-pdf'):
return DocumentType.PDF
else:
raise ValueError(f'Unsupported file type: {file_type}')🧰 Tools🪛 Ruff (0.14.8)59-59: Avoid specifying long messages outside the exception class (TRY003) 🤖 Prompt for AI Agents |
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.